Creating a custom CNN hypertunned architeture for the Fashion MNIST dataset with Python, Keras and Tensorflow.

Overview

custom-cnn-fashion-mnist

Creating a custom CNN hypertunned architeture for the Fashion MNIST dataset with Python, Keras and Tensorflow.

The following hyperparameters were selected for hypertuning with the Grid Search with 5-fold cross-validation strategies:

  • Amount of hidden layers (Convolution + Max Pooling)
  • Number of filters per layer
  • Filter size (H x H)
  • Pool size (B x B)

The best result found was obtained with the following values:

  • Amount of hidden layers (Convolution + Max Pooling): 2
  • Number of filters per layer: 64 on layer 1 and 128 on layer 2
  • Filter Size: (8 x 8)
  • Pool size (3x3)

After training for 30 epochs, an accuracy of 82% was reached in the validation and test sets, demonstrating a high capacity for generalization of the architecture found.


Criando uma arquitetura hipertunada e customizada de CNN (Rede Neural Convolucional) para o conjunto de dados Fashion MNIST com Python, Keras e Tensorflow.

Foram selecionados para hypertuning com as estratégias Grid Search e Validação Cruzada 5-fold os seguintes hiperparâmetros:

  • Quantidade de camadas ocultas (Convolução + Max Pooling)
  • Quantidade de filtros por camada
  • Tamanho do filtro (A x A)
  • Tamanho do pool (B x B)

O melhor resultado encontrado foi obtido com os seguintes valores:

  • Quantidade de camadas ocultas (Convolução + Max Pooling): 2
  • Quantidade de filtros por camada: 64 na camada 1 e 128 na camada 2
  • Tamanho do filtro: (8 x 8)
  • Tamanho do pool (3 x 3)

Após um treino de 30 épocas, alcançou-se uma acurácia nos conjuntos de validação e teste de 82%, demonstrando alta capacidade de generalização da arquitetura encontrada.


Projeto desenvolvido para a disciplina Deep Learning do curso de Especialização em Inteligência Artifical Aplicada, semestre 2021/2, do Instituto Federal de Goiás - Câmpus Goiânia.

Owner
Danielle Almeida
Desenvolvedora de Software | Pesquisadora em Inteligência Artificial
Danielle Almeida
Investigating automatic navigation towards standard US views integrating MARL with the virtual US environment developed in CT2US simulation

AutomaticUSnavigation Investigating automatic navigation towards standard US views integrating MARL with the virtual US environment developed in CT2US

Cesare Magnetti 6 Dec 05, 2022
Audio-Visual Generalized Few-Shot Learning with Prototype-Based Co-Adaptation

Audio-Visual Generalized Few-Shot Learning with Prototype-Based Co-Adaptation The code repository for "Audio-Visual Generalized Few-Shot Learning with

Kaiaicy 3 Jun 27, 2022
DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment

DEEPAGÉ: Answering Questions in Portuguese about the Brazilian Environment This repository is related to the paper DEEPAGÉ: Answering Questions in Por

0 Dec 10, 2021
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

TorchRL Disclaimer This library is not officially released yet and is subject to change. The features are available before an official release so that

Meta Research 860 Jan 07, 2023
This repository contains the source code for the paper Tutorial on amortized optimization for learning to optimize over continuous domains by Brandon Amos

Tutorial on Amortized Optimization This repository contains the source code for the paper Tutorial on amortized optimization for learning to optimize

Meta Research 144 Dec 26, 2022
Exe-to-xlsm - Simple script to create VBscript of exe and inject to xlsm

🎁 Exe To Office Executable file injection to Office documents: .xlsm, .docm, .p

3 Jan 25, 2022
Raptor-Multi-Tool - Raptor Multi Tool With Python

Promises 🔥 20 Stars and I'll fix every error that there is 50 Stars and we will

Aran 44 Jan 04, 2023
Deep Learning Theory

Deep Learning Theory 整理了一些深度学习的理论相关内容,持续更新。 Overview Recent advances in deep learning theory 总结了目前深度学习理论研究的六个方向的一些结果,概述型,没做深入探讨(2021)。 1.1 complexity

fq 103 Jan 04, 2023
Official PyTorch implementation of Data-free Knowledge Distillation for Object Detection, WACV 2021.

Introduction This repository is the official PyTorch implementation of Data-free Knowledge Distillation for Object Detection, WACV 2021. Data-free Kno

NVIDIA Research Projects 50 Jan 05, 2023
Code for our CVPR 2022 Paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection"

GEN-VLKT Code for our CVPR 2022 paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection". Contributed by Yue Lia

Yue Liao 47 Dec 04, 2022
PyTorch implementation of normalizing flow models

PyTorch implementation of normalizing flow models

Vincent Stimper 242 Jan 02, 2023
Unofficial implementation of MUSIQ (Multi-Scale Image Quality Transformer)

MUSIQ: Multi-Scale Image Quality Transformer Unofficial pytorch implementation of the paper "MUSIQ: Multi-Scale Image Quality Transformer" (paper link

41 Jan 02, 2023
Time should be taken seer-iously

TimeSeers seers - (Noun) plural form of seer - A person who foretells future events by or as if by supernatural means TimeSeers is an hierarchical Bay

279 Dec 26, 2022
Multi-Objective Loss Balancing for Physics-Informed Deep Learning

Multi-Objective Loss Balancing for Physics-Informed Deep Learning Code for ReLoBRaLo. Abstract Physics Informed Neural Networks (PINN) are algorithms

Rafael Bischof 16 Dec 12, 2022
Prometheus exporter for Cisco Unified Computing System (UCS) Manager

prometheus-ucs-exporter Overview Use metrics from the UCS API to export relevant metrics to Prometheus This repository is a fork of Drew Stinnett's or

Marshall Wace 6 Nov 07, 2022
Face recognition. Redefined.

FaceFinder Use a powerful CNN to identify faces in images! TABLE OF CONTENTS About The Project Built With Getting Started Prerequisites Installation U

BleepLogger 20 Jun 16, 2021
C3D is a modified version of BVLC caffe to support 3D ConvNets.

C3D C3D is a modified version of BVLC caffe to support 3D convolution and pooling. The main supporting features include: Training or fine-tuning 3D Co

Meta Archive 1.1k Nov 14, 2022
An updated version of virtual model making

Model-Swap-Face v2   这个项目是基于stylegan2 pSp制作的,比v1版本Model-Swap-Face在推理速度和图像质量上有一定提升。主要的功能是将虚拟模特进行环球不同区域的风格转换,目前转换器提供西欧模特、东亚模特和北非模特三种主流的风格样式,可帮我们实现生产资料零成

seeprettyface.com 62 Dec 09, 2022
Python Wrapper for Embree

pyembree Python Wrapper for Embree Installation You can install pyembree (and embree) via the conda-forge package. $ conda install -c conda-forge pyem

Anthony Scopatz 67 Dec 24, 2022
CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum

CO-PILOT CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum, NeurIPS 2021, Shuang Ao, Tianyi Zhou, Guodong Long, Qingh

Shuang Ao 1 Feb 18, 2022